基于用户兴趣的个性化模型研究

大多数搜索引擎没有考虑到用户的个性和兴趣,大大降低了搜索的准确性。采用Web挖掘技术对存放在Web缓存中的历史页面进行挖掘,获取用户的兴趣信息,使用最优二叉树的形式来表示用户兴趣,利用获取的用户兴趣信息来构建个性化模型,并且利用智能Agent跟踪用户的兴趣变化,不断地对用户兴趣个性化模型进行更新。     

基于Agent的个性化信息过滤系统的设计与实现

针对用户个性化服务的特定需求,文中提出了一种基于Agent的个性化信息过滤系统的设计思想及其实现过程。采用基于主题的过滤和基于兴趣的过滤相结合的过滤方法对信息分两次过滤,同时利用Agent跟踪用户的浏览行为,从而提供隐式反馈。系统能够根据文本的内容自动判别文本所属主题分类,并计算待过滤信息与用户兴趣之间的相关度,最后利用用户的反馈对用户兴趣模型进行更新,从而帮助用户准确获取有用信息。     

基于Agent的个性化信息过滤系统的设计与实现

针对用户个性化服务的特定需求，文中提出了一种基于Agent的个性化信息过滤系统的设计思想及其实现过程。采用基于主题的过滤和基于兴趣的过滤相结合的过滤方法对信息分两次过滤，同时利用Agent跟踪用户的浏览行为，从而提供隐式反馈。系统能够根据文本的内容自动判别文本所属主题分类，并计算待过滤信息与用户兴趣之间的相关度，最后利用用户的反馈对用户兴趣模型进行更新，从而帮助用户准确获取有用信息。     

智能搜索引擎的研究与设计

本文根据现有搜索引擎的不足,提出了一个基于MAS的智能元搜索引擎模型。旨在帮助用户快速、准确地获得想要地Web信息。本系统以多Agent技术为基本框架,利用Agent的自治性和协作性来完成智能搜索,并详细讨论了元搜索引擎的建立、用户兴趣模型的建立和用户兴趣的学习。     

基于简化ODP的用户兴趣模型

通过搜集搜索引擎用户的个人兴趣偏好,个性化搜索技术能够对搜索结果中的页面进行分析并与用户的兴趣进行比较,帮助用户从中找出更为感兴趣的结果,从而提高用户的搜索效率。通过利用简化的ODP目录层次结构进行训练以建立基本的用户兴趣树型结构,并在模型使用过程中通过用户的隐式操作反馈,对用户兴趣模型进行动态更新以反映用户不断变化的兴趣偏好。这一用户兴趣建模方法以简化的ODP结构为参考框架,并以用户个人的搜索行为作为模型修正和更新的依据,实现消除词条歧义并且表达用户个人兴趣偏好的目的。     

基于模糊兴趣模型与多Agent的个性化推荐系统

提出了基于模糊兴趣模型与多Agent的个性化推荐系统框架,通过引入用户模糊兴趣模型,使以Agent为基础的推荐系统无法通过隐式收集用户对商品属性评价的问题得到解决,并且在客户端收集并挖掘用户的私有信息,然后从服务器中获取用户感兴趣的信息,最后生成并更新UserProfile。     

基于XML、CORBA和Agent的分布式搜索模型研究

XML、CORBA和Agent各有优势,通过它们的结合,可以克服传统分布式系统的不足。论文分析了传统搜索引擎的不足,提出了一个基于XML、CORBA和Agent技术的分布式信息搜索模型。该系统模型建立在CORBA的基础上,以Agent作为架构系统的基本组件,并用XML进行数据集成。系统还利用Agent的自治性和协作性来完成用户的个性化搜索。最后分析、探讨了基于XML的Agent间的通信语言。     

基于XML、CORBA和Agent的分布式搜索模型研究

XML、CORBA和Agent各有优势,通过它们的结合,可以克服传统分布式系统的不足.论文分析了传统搜索引擎的不足,提出了一个基于XML、CORBA和Agent技术的分布式信息搜索模型.该系统模型建立在CORBA的基础上,以Agent作为架构系统的基本组件,并用XML进行数据集成.系统还利用Agent的自治性和协作性来完成用户的个性化搜索.最后分析、探讨了基于XML的Agent间的通信语言.     

基于搜索历史的用户兴趣模型的研究

提出了一种新的基于搜索历史的用户兴趣模型,目的是解决现有搜索引擎很难考虑用户兴趣来实现用户个性化搜索以及用户兴趣很难更新的问题。提出了基于搜索历史的用户兴趣的表达方法和自动隐式学习算法。全面地描述了用户兴趣模型的建立及通过自动隐式学习算法不断更新、优化模型的处理过程,并给出了对模型的评价标准。     

基于搜索历史的用户兴趣模型的研究

提出了一种新的基于搜索历史的用户兴趣模型，目的是解决现有搜索引擎很难考虑用户兴趣来实现用户个性化搜索以及用户兴趣很难更新的问题。提出了基于搜索历史的用户兴趣的表达方法和自动隐式学习算法。全面地描述了用户兴趣模型的建立及通过自动隐式学习算法不断更新、优化模型的处理过程，并给出了对模型的评价标准。     

基于人物角色的用户建模研究

在以用户为中心的软件设计中,需要通过对用户建模来明确和分析用户,了解用户的特定需求.介绍用户建模的相关概念,阐述基于人物角色的用户建模原理、详细介绍基于人物角色的用户建模过程,指出人物角色在以用户为中心的软件设计过程中的应用.     

A taxonomy of novice user perception of error on the Web

Novice users face many challenges when browsing the Web. The goal of this experiment was to learn about how users perceive error situations when using the World Wide Web. Specifically, the goal was to learn which circumstances cause users to believe that an error has occurred. An exploratory experiment took place with 78 subjects who were novice users. In the experiment the subjects were asked to identify when they perceived that an error had occurred. The subjects reported a total of 219 error situations. These error situations were then classified by the researchers into the following four categories: user error, system error, situational error, and poor Web design. Based on the collected data, suggestions are presented for improving the usability of Web browsers and Web sites.     

基于PageRank的微博用户影响力算法研究

随着Web技术的发展,微博已经成为最受欢迎的社交平台之一了。在中国,微博用户规模已经达到了2.42亿。微博用户影响力计算对社会信息在微博里面有效传播,正确传播,健康传播有着非常重要的意义。本文以新浪微博数据为实验的对象,通过改进传统的PageRank模型,提出了的新型用户影响力排名算法---MBUI-Rank(Micro-Blog User Influence Rank)算法。在考虑传统PageRank方法的用户链接关系的同时,MBUI-Rank算法还考虑到微博用户自身行为活动,构建用户对微博的影响的动态挖掘模型。实验结果表明,MBUI-Rank算法与传统的PageRank算法相比,可以更加真实有效地反映微博用户的实际影响力。     

基于代理的网格用户管理研究

提出了基于代理的网格用户管理机制,实现了网格用户在全局范围内的单一系统登录和对用户全局一致的管理,这种机制避免了对用户集中式管理带来的复杂性和额外的通信带宽,提高了系统对用户的响应速度和用户访问资源与服务的效率.     

Encouraging user participation in a course recommender system: An impact on user behavior

User participation emerged as a critical issue for collaborative and social recommender systems as well as for a range of other systems based on the power of user community. A range of mechanisms to encourage user participation in social systems has been proposed over the last few years; however, the impact of these mechanisms on users behavior in recommender systems has not been studied sufficiently. This paper investigates the impact of encouraging user participation in the context of CourseAgent, a community-based course recommender system. The recommendation power of CourseAgent is based on course ratings provided by a community of students. To increase the number of course ratings, CourseAgent applies an incentive mechanism which turns user feedback into a self-beneficial activity. In this paper, we describe the design and implementation of our course recommendation system and its incentive mechanism. We also report a dual impact of this mechanism on user behavior discovered in two user studies.     

Selecting users for participation in IT projects: Trading a representative sample for advocates and champions?

The selection of users for participation in IT projects involves trade-offs between multiple criteria, one of which is selecting a representative cross-section of users. This criterion is basic because trading it for other criteria means basing designs on information biased toward some user groups at the expense of others. Based on interviews in development and customer organizations we find that their criteria for user selection favor persons who can contribute to the progress of the IT project over persons who are representative of the full range of users. A highly valued contribution from participating users is the ability to advocate a vision for the system and champion its organizational implementation. A survey in one customer organization shows that respondents’ personal traits explain up to 31% of the variation in their experience of aspects of the usability of a recently introduced system. Thus, unless participating users are representative as to these personal traits, IT projects may, inadvertently, bring about systems that will fail to satisfy many users.     

基于XML的统一用户界面描述

提出一种与具体语言和工具都无关的统一描述方法，即基于XML的统一用户界面描述，以作为不同的应用程序之间相互交流的基础，为用户界面的重用性发展和向下一代用户界面的顺利发展打下良好的基础。先概述用户界面的发展和当前存在的问题，然后阐述基于XML的统一用户界面的定义、实现方式以及如何在浏览器中进行模拟显示，最后对盯应的支持工具和应用模式进行探讨和展望。     

A psychometric user experience model based on fuzzy measure approaches

User experience (UX) is considered a key quality of interactive products in today’s competitive mass markets and is of growing interest in both academia and industry. UX concerns the encounters a user has while interacting with products, systems, and services. It is ubiquitous, omnipresent, and dynamic in nature, referring to the non-quantifiable, subjective, affective-based, and context-dependent processes. UX is difficult for researchers to objectively and uniformly measure as it involves complex human perceptual interpretations of experiential responses with a certain degree of uncertainty, imprecision, and vagueness. Based on the user experience questionnaire (UEQ), this paper presents a psychometric UX model using fuzzy measure approaches, the purpose of which is to develop a metric for quantitative assessment of certain product UXs through a user experience index (UXI). This model enables researchers to understand users’ perceptions of the interactions that constitute qualities of using a specific product. An empirical study concerning the episodic UX measures of using a set of touch mice was conducted to verify the applicability and effectiveness of the proposed UX model. The theoretical and practical implications of the UX model are also discussed.     

社会化推荐系统的研究进展综述

对社会网络环境下构建个性化推荐系统的现有技术进行综述。介绍社会网络的基本概念,简述推荐系统的应用领域和目前面临的挑战,重点介绍社会化推荐的相关技术的研究现状,包括用户生成内容、社会化标签推荐、博客挖掘和基于信任的推荐,分析社会化推荐面临的主要问题。利用Web 2．0环境下的用户生成内容,为解决用户配置和冷启动问题提供一个研究方向。     

Stratified analysis of AOL query log

Characterizing user’s intent and behaviour while using a retrieval information tool (e.g. a search engine) is a key question on web research, as it hold the keys to know how the users interact, what they are expecting and how we can provide them information in the most beneficial way. Previous research has focused on identifying the average characteristics of user interactions. This paper proposes a stratified method for analyzing query logs that groups queries and sessions according to their hit frequency and analyzes the characteristics of each group in order to find how representative the average values are. Findings show that behaviours typically associated with the average user do not fit in most of the aforementioned groups.